Reinforcement Learning Engineer – Robotics

About the role

Technology Innovation Institute (TII) is seeking a Reinforcement Learning Engineer to advance robotics, swarm intelligence, and drone systems. The role combines theoretical RL research with practical deployment in real‑world environments, focusing on scalable, distributed control solutions.

Key responsibilities

• Design, implement, and optimise RL algorithms for robotic platforms, UAV swarms and autonomous agents.
• Develop multi‑agent reinforcement learning (MARL) frameworks for coordination, de‑confliction and cooperative decision‑making in multi‑drone systems.
• Build efficient training pipelines for large‑scale simulations and improve simulation‑to‑real transfer performance.
• Stay current with state‑of‑the‑art RL methods and investigate hybrid learning paradigms such as neurosymbolic and model‑based/model‑free hybrids.

Required profile

• Master’s or PhD in Computer Science, Robotics, AI/ML or a related field.
• Proven experience implementing RL solutions for robotics or UAV applications.
• Strong background in policy‑gradient, Q‑learning, actor‑critic and hierarchical RL techniques.

Required skills

• Python and C++ programming.
• RL frameworks: Ray RLlib, Stable Baselines3.
• Simulation environments: PyBullet, Isaac Gym, Gazebo, MuJoCo, AirSim.
• AI frameworks: PyTorch, TensorFlow, JAX.
• Docker, distributed training systems, GPU clusters, CUDA.
• Robotics middleware integration: ROS2, PX4, MAVSDK.